Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical and programming variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.73
    s
    0.53
    er
    0.51
    ی
    0.46
    𝗯
    0.45
    ak
    0.44
    𝗳
    0.44
    bies
    0.44
    in
    0.43
     automatic
    0.43
    POSITIVE LOGITS
    0.54
     Consultado
    0.40
     hundert
    0.40
     ofthe
    0.40
     that
    0.39
     calcular
    0.38
     presidente
    0.38
     WUE
    0.38
     pouces
    0.38
    Request
    0.37
    Act Density 0.412%

    No Known Activations